Learning disentangled representations to harmonize connectome network measures.

Purpose: Connectome network metrics are commonly regarded as fundamental properties of the brain, and their alterations have been implicated in the development of Alzheimer's disease, multiple sclerosis, and traumatic brain injury. However, these metrics are actually estimated properties through a multistage propagation from local voxel diffusion estimations, regional tractography, and region of interest mapping. These estimation processes are significantly influenced by choices specific to imaging protocols and software, producing site-wise effects.

Approach: Recent advances in disentanglement techniques offer opportunities to learn representational spaces that separate factors that cause domain shifts from intrinsic biological factors. Although these techniques have been applied in unsupervised brain anomaly detection and image-level features, their application to the unique manifold structures of connectome adjacency matrices remains unexplored. Here, we explore the conditional variational autoencoder structure for generating site-invariant representations of the connectome, allowing the harmonization of brain network measures.

Results: Focusing on the context of aging, we conducted a study involving 823 patients across two sites. This approach effectively segregates site-specific influences from biological features, aligns network measures across different domains (Cohen's $D<0.2$ and Mann-Whitney $U\text{-}\text{test}<0.05$ ), and maintains associations with age ( $2.71\times {10}^{-02}\pm 2.86\times {10}^{-03}$ error in years) and sex ( $0.92\pm 0.02$ accuracy).

Conclusions: Our findings demonstrate that using latent representations significantly harmonizes network measures and provides robust metrics for multi-site brain network analysis.